I'm wondering how to go about evaluating the long term effects of a biological intervention, like a new therapeutic. There is emergent evidence that common medications like NSAIDs or anticholinergics significantly increase the risk of heart disease and dementia respectively. It seems to me that many therapeutics could have similarly devastating long-term effects, and we've found the side effects in NSAIDs and anticholinergics because they're some of the most commonly consumed medicines.

Thus, I want to know how to think about long-term effects, and if any frameworks are in use today to consider potential long-term effects.

There are a couple derivative questions I sought to answer:

  1. To what degree are long term side effects preceded by detectable short term side effects?
  2. Are there common systems in which damage accumulates over the long term, reaching a threshold that causes catastrophic damage?

1 Answer 1


The long-term side effects are typically studied within the framework of the survival analysis. E.g., a cohort if individuals is followed throughout many years, recording the number of cases of adverse side effects and deaths, or none happening (censored data). Previous medicalninterventions, short-term side effects, and other risk factors are included as statistical covariates. One can then use the methods of the survival analysis, such as Cox regression, to establish whether any of these risk factors is related to the incidence of the adverse conditions.

In the context of new types of medication/intervention, such a study essentially constitutes the Phase IV clinical study, which often lasts throughout all the time while the medication/intervention is in use.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.